Akhil Galla's Projects
Paper Lists for Graph Neural Networks
Master programming by recreating your favorite technologies from scratch.
Q. Liu, L. Xiao, J. Yang and Z. Wei, "CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification," in IEEE Transactions on Geoscience and Remote Sensing, doi: 10.1109/TGRS.2020.3037361.
An improved version of the color name model described here: http://lewisandquark.tumblr.com/post/160776374467/new-paint-colors-invented-by-neural-network.
Advanced Topics in Artificial Intelligence, NUS CS6208, 2023
Datasets for deep learning with satellite & aerial imagery
Simulation and performance analysis of 3 benchmark models (Standard U-Net, U-Net with Resnet backbone & U-Net with DeepLabV3+ backbone) for Multiclass Semantic Segmentation of Satellite Images.
Implementation of Graph Convolutional Networks in TensorFlow
A repo for holding example code
Graph Neural Network Tutorial
Google Research
This is a guide for how one can prepare for GRE within a month's duration.
CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer
Multiscale Dynamic Graph Convolutional Network for hyperspectral image classification
NITRO (NITFio, "R" is a ligature for "Fi") is a full-fledged, extensible library solution for reading and writing the National Imagery Transmission Format (NITF), a U.S. DoD standard format. It is written in cross-platform C, with bindings available for other languages.
Sample code from the Neural Networks from Scratch book.
An autoencoder that performs nonlinear pixel unmixing on hyperspectral images (based on the Fan, Bilinear, PPNM models, and also higher order nonlinear terms)
Implementation of paper "Nonlinear Unmixing of Hyperspectral Data via Deep Autoencoder Networks" (GRSL 2019)
Graph Neural Network Library for PyTorch, codes of different architectures in examples
RelTR: Relation Transformer for Scene Graph Generation: https://arxiv.org/abs/2201.11460v2
Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).
official implementation for the paper "Simplifying Graph Convolutional Networks"
StyleGAN Encoder - converts real images to latent space
A single player Tic Tac Toe game built using React.